Disaggregated Quantization: Specializing LLM Prefill and Decode Paper • 2609.26333 • Published 11 days ago • 91
GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling Paper • 2608.29335 • Published Aug 29 • 73
Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation Paper • 2601.22813 • Published Jan 30 • 63
PingPong: A Benchmark for Role-Playing Language Models with User Emulation and Multi-Model Evaluation Paper • 2409.06820 • Published Sep 10, 2024 • 68
Saiga Collection Russian fine-tunes of different base LLMs • 12 items • Updated Apr 25, 2025 • 45